© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 5989
    Prev
    Next
    INDEX
    Explanations

    references to programming concepts and structures, particularly functions, methods, and interfaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Niedersch
    -0.34
     Sales
    -0.33
    zuführen
    -0.32
     Kesehatan
    -0.32
     Autres
    -0.31
     Dating
    -0.30
     system
    -0.30
     Trauer
    -0.30
    Sales
    -0.29
     mulia
    -0.28
    POSITIVE LOGITS
     Technique
    1.02
     Method
    1.01
    Method
    0.99
    Condition
    0.99
    Technique
    0.98
     Condition
    0.94
    Situation
    0.93
     Procedure
    0.92
    Procedure
    0.91
    Pattern
    0.91
    Activations Density 0.466%

    No Known Activations